Golang Selection.Text方法代码示例

// Add street to result and find street information (to WikipediaMoscow.result)
func (parser *WikipediaMoscow) processLink(_ int, s *goquery.Selection, done chan<- *StreetInfo) {
	name := strings.TrimSpace(s.Text())
	if len(name) == 0 {
		done <- parser.getEmptyInfo("")
		return
	}

	href, exists := s.Attr("href")
	if !exists {
		done <- parser.getEmptyInfo("")
		return
	}

	var (
		class string
		info  *StreetInfo
	)

	class, exists = s.Attr("class")

	if exists && class == "new" {
		info = parser.getEmptyInfo(name)
	} else if resp, err := http.Get(parser.baseURL + href); err != nil {
		info = parser.getEmptyInfo(name)
	} else {
		streetparser := NewWikipediaStreetParser()
		info, err = streetparser.ParseStreetInfo(name, resp.Body)
		if err != nil {
			info = parser.getEmptyInfo(name)
		}
	}
	done <- info
}

// node returns a string representation of the selection.
func node(i int, s *goquery.Selection) string {
	switch node := s.Get(0); {
	case node.Data == "h1":
		return fmt.Sprintf(" \033[%dm# %s\033[0m\n\n", blue, text(s))
	case node.Data == "h2":
		return fmt.Sprintf(" \033[%dm## %s\033[0m\n\n", blue, text(s))
	case node.Data == "h3":
		return fmt.Sprintf(" \033[%dm### %s\033[0m\n\n", blue, text(s))
	case node.Data == "p":
		return fmt.Sprintf("\033[%dm%s\033[0m\n\n", none, indent(text(s), 1))
	case node.Data == "pre" || s.HasClass("highlight"):
		return fmt.Sprintf("\033[1m%s\033[0m\n\n", indent(text(s), 2))
	case node.Data == "a":
		return fmt.Sprintf("%s (%s) ", s.Text(), s.AttrOr("href", "missing link"))
	case node.Data == "li":
		return fmt.Sprintf("  • %s\n", contents(s))
	case node.Data == "ul":
		return fmt.Sprintf("%s\n", nodes(s))
	case node.Data == "code":
		return fmt.Sprintf("\033[1m%s\033[0m ", s.Text())
	case node.Type == html.TextNode:
		return strings.TrimSpace(node.Data)
	default:
		return ""
	}
}

func ScrapeExamples(s *goquery.Selection) []string {
	examples := []string{}
	s.Find("span.h").Each(func(i int, s *goquery.Selection) {
		examples = append(examples, s.Text())
	})
	return examples
}

func JoinNodesWithSpace(s *goquery.Selection) string {
	texts := []string{}
	s.Each(func(i int, s *goquery.Selection) {
		texts = append(texts, s.Text())
	})
	return strings.Join(texts, " ")
}

func parseColors(s *goquery.Selection) string {
	colors := ""
	s.Each(func(i int, s *goquery.Selection) {
		colors += s.Text()
	})
	return colors
}

func (this *contentExtractor) getSiblingsContent(currentSibling *goquery.Selection, baselinescoreSiblingsPara float64) []*goquery.Selection {
	ps := make([]*goquery.Selection, 0)
	if currentSibling.Get(0).DataAtom.String() == "p" && len(currentSibling.Text()) > 0 {
		ps = append(ps, currentSibling)
		return ps
	} else {
		potentialParagraphs := currentSibling.Find("p")
		potentialParagraphs.Each(func(i int, s *goquery.Selection) {
			text := s.Text()
			if len(text) > 0 {
				ws := this.config.stopWords.stopWordsCount(this.config.targetLanguage, text)
				paragraphScore := ws.stopWordCount
				siblingBaselineScore := 0.30
				highLinkDensity := this.isHighLinkDensity(s)
				score := siblingBaselineScore * baselinescoreSiblingsPara
				if score < float64(paragraphScore) && !highLinkDensity {
					node := new(html.Node)
					node.Type = html.TextNode
					node.Data = text
					node.DataAtom = atom.P
					nodes := make([]*html.Node, 1)
					nodes[0] = node
					newSelection := new(goquery.Selection)
					newSelection.Nodes = nodes
					ps = append(ps, newSelection)
				}
			}

		})
	}
	return ps
}

func (rc *TwitterChecker) findSigInTweet(h SigHint, s *goquery.Selection) ProofError {

	inside := s.Text()
	html, err := s.Html()

	checkText := h.checkText

	if err != nil {
		return NewProofError(keybase1.ProofStatus_CONTENT_FAILURE, "No HTML tweet found: %s", err)
	}

	G.Log.Debug("+ Checking tweet '%s' for signature '%s'", inside, checkText)
	G.Log.Debug("| HTML is: %s", html)

	rxx := regexp.MustCompile(`^(@[a-zA-Z0-9_-]+\s+)`)
	for {
		if m := rxx.FindStringSubmatchIndex(inside); m == nil {
			break
		} else {
			prefix := inside[m[2]:m[3]]
			inside = inside[m[3]:]
			G.Log.Debug("| Stripping off @prefx: %s", prefix)
		}
	}
	if strings.HasPrefix(inside, checkText) {
		return nil
	}

	return NewProofError(keybase1.ProofStatus_DELETED, "Could not find '%s' in '%s'",
		checkText, inside)
}

//a lot of times the first paragraph might be the caption under an image so we'll want to make sure if we're going to
//boost a parent node that it should be connected to other paragraphs, at least for the first n paragraphs
//so we'll want to make sure that the next sibling is a paragraph and has at least some substatial weight to it
func (this *contentExtractor) isBoostable(node *goquery.Selection) bool {
	stepsAway := 0
	next := node.Next()
	for next != nil && stepsAway < node.Siblings().Length() {
		currentNodeTag := node.Get(0).DataAtom.String()
		if currentNodeTag == "p" {
			if stepsAway >= 3 {
				if this.config.debug {
					log.Println("Next paragraph is too far away, not boosting")
				}
				return false
			}

			paraText := node.Text()
			ws := this.config.stopWords.stopWordsCount(this.config.targetLanguage, paraText)
			if ws.stopWordCount > 5 {
				if this.config.debug {
					log.Println("We're gonna boost this node, seems content")
				}
				return true
			}
		}

		stepsAway++
		next = next.Next()
	}

	return false
}

func getDataFromDOM(s *gq.Selection, arr []string, code string) string {
	var dt string
	if arr[0] == "text" {
		dt = s.Text()
	} else {
		dt, _ = s.Attr(arr[0])
	}
	return encode_string(dt, code)
}

func (e extractContent) noParasWithoutTable(s *goquery.Selection) bool {
	s.FindMatcher(pTags).Each(func(i int, s *goquery.Selection) {
		if len(s.Text()) < 25 {
			s.Remove()
		}
	})

	return s.FindMatcher(pTags).Length() == 0 && !nodeIs(s.Nodes[0], atom.Td)
}

func (d *Document) getLinkDensity(s *goquery.Selection) float32 {
	linkLength := len(s.Find("a").Text())
	textLength := len(s.Text())

	if textLength == 0 {
		return 0
	}

	return float32(linkLength) / float32(textLength)
}

func parseHeader(element *goquery.Selection, info *TrainInfo) {
	element.Find("span").Each(func(i int, element *goquery.Selection) {
		switch i {
		case 0:
			info.Category, info.Number, info.Name = parseTrainDenomination(element.Text())
		case 2:
			info.From, info.To = parseTrainRoute(element.Text())
		}
	})
}

func displayDetails(single *goquery.Selection) {
	text := strings.TrimSpace(single.Text())
	href, _ := single.Attr("href")
	length := utf8.RuneCountInString(text)
	if ((length > 5) && wordExists(text, "keywords")) || ((length > 5) && wordExists(href, "keywords")) {
		if wordExists(text, "products") {
			fmt.Println("Link", single.Text(), "--->", href)
		}
	}

}

func parseResource(s *goquery.Selection) (_production, _stored, _capacity int) {
	productionStr, _ := s.Attr("title")
	production, _ := strconv.Atoi(productionStr)

	status := s.Text()
	split := strings.Split(status, "/")

	stored, _ := strconv.Atoi(split[0])
	capacity, _ := strconv.Atoi(split[1])

	return production, stored, capacity
}

func addIngredient(ingredients []data.Ingredient, a *goquery.Selection) []data.Ingredient {
	if href, ok := a.Attr("href"); ok {
		glog.V(2).Info("    href: " + href)
		id, err := strconv.Atoi(strings.Split(href, "/")[2])
		if err != nil {
			glog.Errorf("Failed to extract id from %s: %v", href, err)
		} else {
			ingredients = append(ingredients, data.Ingredient{Name: a.Text(), Id: id})
		}
	}
	return ingredients
}